Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    bad movie reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retrieval
    -0.07
     인천
    -0.07
     debates
    -0.07
    Orders
    -0.07
     ogr
    -0.07
     ITE
    -0.07
    ADDE
    -0.07
     UNIVERS
    -0.06
    風
    -0.06
     sovere
    -0.06
    POSITIVE LOGITS
     muschi
    0.06
     أع
    0.06
    Tu
    0.06
    (thing
    0.06
     uneven
    0.06
     ورزش
    0.06
    (blank
    0.06
    _WORK
    0.06
    redirectToRoute
    0.05
    (recv
    0.05
    Act Density 0.077%

    No Known Activations